Hadoop MR JSON example

WordCount.java

import java.io.IOException;
import java.util.*;
        
import org.codehaus.jackson.map.ObjectMapper;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;
        
public class WordCount {
        
 public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> {
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
	private ObjectMapper mapper = new ObjectMapper();
        
    public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
        String line = value.toString();
		java.util.Map<String,String> rootAsMap = mapper.readValue(line, java.util.Map.class);
        StringTokenizer tokenizer = new StringTokenizer(rootAsMap.get("text"));
        while (tokenizer.hasMoreTokens()) {
            word.set(tokenizer.nextToken());
            output.collect(word, one);
        }
    }
 } 
        
 public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {

    public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
        int sum = 0;
        while (values.hasNext()) {
            sum += values.next().get();
        }
        output.collect(key, new IntWritable(sum));
    }
 }
        
 public static void main(String[] args) throws Exception {
    JobConf conf = new JobConf(WordCount.class);
    conf.setJobName("wordcount");
        
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);
        
    conf.setMapperClass(Map.class);
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);
        
    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);
        
    /* Deprecated ?
     * conf.setInputPath(new Path(args[0]));
     * conf.setOutputPath(new Path(args[1]));
     */

    FileInputFormat.setInputPaths(conf, new Path(args[0]));
    FileOutputFormat.setOutputPath(conf, new Path(args[1]));
        
    JobClient.runJob(conf);
 }
        
}

wget http://apache.mirrors.hoobly.com//hadoop/common/hadoop-0.20.205.0/hadoop-0.20.205.0.tar.gz
export HADOOP_CP=hadoop-ant-0.20.205.0.jar:hadoop-core-0.20.205.0.jar:hadoop-examples-0.20.205.0.jar:hadoop-test-0.20.205.0.jar:hadoop-tools-0.20.205.0.jar:lib/jackson-mapper-asl-1.0.1.jar:lib/jackson-core-asl-1.0.1.jar
javac -cp $HADOOP_CP -d wordcount_classes WordCount.java
jar -cvf wordcount.jar -C wordcount_classes .